Abstract Federated Learning (FL, or Collaborative Learning (CL)) has surely gained a
reputation for not only building Machine Learning (ML) models that rely on distributed …

Real-world graphs such as social networks, communication networks, and rating networks
are constantly evolving over time. Many deep learning architectures have been developed …

An adversary intercepts a stream of images between a sender and a receiver neural network
classifier. To minimize its footprint, the adversary only attacks a limited number of images …

Generative models have grown into the workhorse of many state-of-the-art machine learning
methods. However, their vulnerability under poisoning attacks has been largely …

Data economy relies on data-driven systems and complex machine learning applications
are fueled by them. Unfortunately, however, machine learning models are exposed to …

Deep neural networks, particularly in vision tasks, are notably susceptible to adversarial
perturbations. To overcome this challenge, developing a robust classifier is crucial. In light of …

Recent research has demonstrated that machine learning algorithms are vulnerable to
adversarial attacks, in which small but carefully crafted input perturbations can lead to …

An adversary wants to attack a limited number of images within a stream of known length to
reduce the exposure risk. Also, the adversary wants to maximize the success rate of the …

An adversary intercepts a stream of images between a sender and a receiver neural network
classifier. To minimize its footprint, the adversary only attacks a limited number of images …

This thesis explores the realm of machine learning (ML), focusing on enhancing model
interpretability called interpretable machine learning (IML) techniques. The initial chapter …